| 苹果果梗和缺陷的识别技术研究 |
| |
| 引用本文： | 黄星奕,林建荣,赵杰文. 苹果果梗和缺陷的识别技术研究[J]. 江苏大学学报(自然科学版), 2004, 25(3): 193-195 |
| |
| 作者姓名： | 黄星奕 林建荣 赵杰文 |
| |
| 作者单位： | 江苏大学生物与环境工程学院,江苏,镇江,212013;江苏大学生物与环境工程学院,江苏,镇江,212013;江苏大学生物与环境工程学院,江苏,镇江,212013 |
| |
| 基金项目： | 江苏省自然科学基金资助项目(BK2002005)，国家863计划项目(2002AA248051) |
| |
| 摘 要： | 为解决苹果自动检测和分选中苹果果梗和缺陷的识别这一瓶颈问题，提出基于HIS颜色模型下亮度，的分布特性，从信号处理的角度确定苹果的果梗和缺陷区域．再提取区域纹理特征，构筑模拟退火神经网络作为模式分类器，区分果梗和缺陷．试验结果表明用该方法识别准确率接近90％．为苹果的在线检测和分级打下了良好的基础．
|
| 关 键 词： | 苹果 识别 计算机视觉 神经网络 |
| 文章编号： | 1671-7775(2004)03-0193-03 |
| 修稿时间： | 2003-12-31 |
Identification technique for stem-end and blemish in apples |
| |
| HUANG Xing-yi,LIN Jian-rong,ZHAO Jie-wen. Identification technique for stem-end and blemish in apples[J]. Journal of Jiangsu University:Natural Science Edition, 2004, 25(3): 193-195 |
| |
| Authors: | HUANG Xing-yi LIN Jian-rong ZHAO Jie-wen |
| |
| Abstract: | A new method was developed to identify stem-end and blemish in apples precisely. Stem-end and blemish in apples were determined using one-dimension signal processing method based on HIS color model. By taking texture parameters of those two areas as input, a simulated annealing neural network was developed to identify stem-end and blemish in apples. Results show that the new technique is precise and effective in identification, and is feasible for practical apple sorting. |
| |
| Keywords: | apple identification computer vision neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
